A speech parameter generation algorithm considering global variance for HMM-based speech synthesisTODA, Tomoki; TOKUDA, Keiichi.IEICE transactions on information and systems. 2007, Vol 90, Num 5, pp 816-824, issn 0916-8532, 9 p.Article

Statistical Voice Conversion Techniques for Body-Conducted Unvoiced Speech EnhancementTODA, Tomoki; NAKAGIRI, Mikihiro; SHIKANO, Kiyohiro et al.IEEE transactions on audio, speech, and language processing. 2012, Vol 20, Num 9, pp 2505-2517, issn 1558-7916, 13 p.Article

An evaluation of cost functions sensitively capturing local degradation of naturalness for segment selection in concatenative speech synthesisTODA, Tomoki; KAWAI, Hisashi; TSUZAKI, Minoru et al.Speech communication. 2006, Vol 48, Num 1, pp 45-56, issn 0167-6393, 12 p.Article

Adaptive Training for Voice Conversion Based on EigenvoicesOHTANI, Yamato; TODA, Tomoki; SARUWATARI, Hiroshi et al.IEICE transactions on information and systems. 2010, Vol 93, Num 6, pp 1589-1598, issn 0916-8532, 10 p.Article

Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture modelTODA, Tomoki; BLACK, Alan W; TOKUDA, Keiichi et al.Speech communication. 2008, Vol 50, Num 3, pp 215-227, issn 0167-6393, 13 p.Article

Improvements of the One-to-Many Eigenvoice Conversion System : Processing natural speech variability for improved verbal human-computer interactionOHTANI, Yamato; TODA, Tomoki; SARUWATARI, Hiroshi et al.IEICE transactions on information and systems. 2010, Vol 93, Num 9, pp 2491-2499, issn 0916-8532, 9 p.Article

Reducing computation time of the rapid unsupervised speaker adaptation based on HMM-sufficient statisticsGOMEZ, Randy; TODA, Tomoki; SARUWATARI, Hiroshi et al.IEICE transactions on information and systems. 2007, Vol 90, Num 2, pp 554-561, issn 0916-8532, 8 p.Article

Voice conversion based on maximum-likelihood estimation of spectral parameter trajectoryTODA, Tomoki; BLACK, Alan W; TOKUDA, Keiichi et al.IEEE transactions on audio, speech, and language processing. 2007, Vol 15, Num 8, pp 2222-2235, issn 1558-7916, 14 p.Article

An evaluation of automatic phone segmentation for concatenative speech synthesisKAWAI, Hisashi; TODA, Tomoki.ICASSP. 2004, isbn 0-7803-8484-9, vol I, 677-680Conference Paper

Speaking-aid systems using GMM-based voice conversion for electrolaryngeal speechNAKAMURA, Keigo; TODA, Tomoki; SARUWATARI, Hiroshi et al.Speech communication (Print). 2012, Vol 54, Num 1, pp 134-146, issn 0167-6393, 13 p.Article

Techniques in rapid unsupervised speaker adaptation based on HMM-Sufficient StatisticsGOMEZ, Randy; TODA, Tomoki; SARUWATARI, Hiroshi et al.Speech communication (Print). 2009, Vol 51, Num 1, pp 42-57, issn 0167-6393, 16 p.Article

Cost Reduction of Acoustic Modeling for Real-Environment Applications Using Unsupervised and Selective Training : Robust speech processing in realistic environmentsCINCAREK, Tobias; TODA, Tomoki; SARUWATARI, Hiroshi et al.IEICE transactions on information and systems. 2008, Vol 91, Num 3, pp 499-507, issn 0916-8532, 9 p.Article

The Nitech-NAIST HMM-Based Speech Synthesis System for the Blizzard Challenge 2006ZEN, Heiga; TODA, Tomoki; TOKUDA, Keiichi et al.IEICE transactions on information and systems. 2008, Vol 91, Num 6, pp 1764-1773, issn 0916-8532, 10 p.Article

Utterance-based selective training for the automatic creation of task-dependent acoustic models : Statistical modeling for speech processingCINCAREK, Tobias; TODA, Tomoki; SARUWATARI, Hiroshi et al.IEICE transactions on information and systems. 2006, Vol 89, Num 3, pp 962-969, issn 0916-8532, 8 p.Article

Building an Effective Speech Corpus by Utilizing Statistical Multidimensional Scaling Method : Robust speech processing in realistic environmentsNAGINO, Goshu; SHOZAKAI, Makoto; TODA, Tomoki et al.IEICE transactions on information and systems. 2008, Vol 91, Num 3, pp 607-614, issn 0916-8532, 8 p.Article

Alaryngeal Speech Enhancement Based on One-to-Many Eigenvoice ConversionDOI, Hironori; TODA, Tomoki; NAKAMURA, Keigo et al.IEEE/ACM transactions on audio, speech, and language processing. 2014, Vol 22, Num 1-2, pp 172-183, 12 p.Article

Esophageal Speech Enhancement Based on Statistical Voice Conversion with Gaussian Mixture Models : Processing natural speech variability for improved verbal human-computer interactionDOI, Hironori; NAKAMURA, Keigo; TODA, Tomoki et al.IEICE transactions on information and systems. 2010, Vol 93, Num 9, pp 2472-2482, issn 0916-8532, 11 p.Article

Improving rapid unsupervised speaker adaptation based on HMM-sufficient statistics in noisy environments using multi-template models : Statistical modeling for speech processingGOMEZ, Randy; LEE, Akinobu; TODA, Tomoki et al.IEICE transactions on information and systems. 2006, Vol 89, Num 3, pp 998-1005, issn 0916-8532, 8 p.Article

Designing target cost function based on prosody of speech database : Corpus-Based Speech TechnologiesADACHI, Kazuki; TODA, Tomoki; KAWANAMI, Hiromichi et al.IEICE transactions on information and systems. 2005, Vol 88, Num 3, pp 519-524, issn 0916-8532, 6 p.Article

Optimizing sub-cost functions for segment selection based on perceptual evaluations in concatenative speech synthesisTODA, Tomoki; KAWAI, Hisashi; TSUZAKI, Minoru et al.ICASSP. 2004, isbn 0-7803-8484-9, vol I, 657-660Conference Paper

Improvement to a NAM-captured whisper-to-speech systemTRAN, Viet-Anh; BAILLY, Gérard; LŒVENBRUCK, Hélène et al.Speech communication (Print). 2010, Vol 52, Num 4, pp 314-326, issn 0167-6393, 13 p.Article

Speech Synthesis Based on Hidden Markov ModelsTOKUDA, Keiichi; NANKAKU, Yoshihiko; TODA, Tomoki et al.Proceedings of the IEEE. 2013, Vol 101, Num 5, pp 1234-1252, issn 0018-9219, 19 p.Article

Silent-speech enhancement using body-conducted vocal-tract resonance signalsHIRAHARA, Tatsuya; OTANI, Makoto; SHIMIZU, Shota et al.Speech communication (Print). 2010, Vol 52, Num 4, pp 301-313, issn 0167-6393, 13 p.Article

Robust Speaker-Adaptive HMM-Based Text-to-Speech SynthesisYAMAGISHI, Junichi; NOSE, Takashi; HEIGA ZEN et al.IEEE transactions on audio, speech, and language processing. 2009, Vol 17, Num 6, pp 1208-1230, issn 1558-7916, 23 p.Article